© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 99207
    Prev
    Next
    INDEX
    Explanations

    random snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    cth
    -0.25
    mx
    -0.24
    icator
    -0.24
    jsx
    -0.24
    æĸ¹éĿ¢
    -0.24
    佩æľį
    -0.24
    人å¿ĥ
    -0.24
    lix
    -0.23
    èĥ½åĬĽåĴĮ
    -0.23
    åĵĴ
    -0.22
    POSITIVE LOGITS
     Eb
    0.27
    SPA
    0.25
     dumpster
    0.25
    åĨľè´¸
    0.23
    åĪ°ä½į
    0.23
    ç£ĭ
    0.23
    amedi
    0.23
    æ³®
    0.23
    _def
    0.23
    ambio
    0.22
    Activations Density 0.347%

    No Known Activations